Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper nouns, likely related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific entities or names, particularly related to individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llor
    -0.82
    furt
    -0.67
    ventus
    -0.67
    ���
    -0.66
     Lans
    -0.66
     Samoa
    -0.66
    Bul
    -0.65
    ctors
    -0.64
     DirectX
    -0.64
    ģ
    -0.64
    POSITIVE LOGITS
    apped
    0.84
    uba
    0.81
    bean
    0.81
    ours
    0.80
    oded
    0.78
    attery
    0.78
    ryn
    0.77
    aps
    0.77
    uana
    0.76
    uncle
    0.76
    Act Density 0.034%

    No Known Activations